Open-source Python OCR library that detects and recognizes text in PDFs and images using deep learning models, built on PyTorch.
6,4 mil687PythonApache-2.0Atualizado há 2 horas
sczhou/CodeFormer
Python tool for blind face restoration, enhancing blurry, low-quality or damaged faces in photos and videos using a codebook lookup transformer.
- Estrelas
- 18,185
- Forks
- 3,723
- Issues abertas
- 283
- Último commit
- há 11 meses
O que é?
CodeFormer restores faces in images and videos when the degradation type is unknown, a setting called blind face restoration. It is the official implementation of a NeurIPS 2022 paper that uses a learned codebook of facial priors and a transformer to predict clean facial details from degraded input.
The tool exposes a fidelity weight that trades off output quality against similarity to the original face, so users can favor cleaner results or closer identity. Beyond restoration, it includes scripts for colorizing black-and-white or faded face photos and for inpainting masked regions of aligned faces.
For whole images and video, it can enhance background regions with Real-ESRGAN and upsample the restored face. Pretrained models are downloaded via a provided script, and the project includes training code and configuration files.
Recursos principais
- 01Blind face restoration for images and cropped, aligned 512x512 faces
- 02Adjustable fidelity weight to balance quality and similarity to the input
- 03Video enhancement from .mp4, .mov and .avi inputs
- 04Face colorization for black-and-white or faded photos
- 05Face inpainting for masked regions
- 06Optional Real-ESRGAN background enhancement and face upsampling
Casos de uso
- Restoring old or low-resolution family photos
- Enhancing blurry frames in older video clips
- Fixing distorted faces in AI-generated art
- Researchers comparing blind face restoration methods on aligned face datasets
Tópicos
Perguntas frequentes
- O que é CodeFormer?
- Python tool for blind face restoration, enhancing blurry, low-quality or damaged faces in photos and videos using a codebook lookup transformer. CodeFormer restores faces in images and videos when the degradation type is unknown, a setting called blind face restoration. It is the official implementation of a NeurIPS 2022 paper that uses a learned codebook of facial priors and a transformer to predict clean facial details from degraded input.
- CodeFormer é gratuito? Qual é a licença?
- CodeFormer é open source sob a licença Other. Confira os termos da licença antes de usá-lo em produtos comerciais.
- CodeFormer ainda é mantido?
- Sem commits há mais de 6 meses. O último commit de CodeFormer foi em 18 de nov. de 2025.
- Para que posso usar CodeFormer?
- Restoring old or low-resolution family photos Enhancing blurry frames in older video clips Fixing distorted faces in AI-generated art Researchers comparing blind face restoration methods on aligned face datasets
- Onde consigo CodeFormer?
- O código-fonte e as instruções de instalação estão no GitHub: https://github.com/sczhou/CodeFormer
Resumo gerado por IA a partir do README do projeto. As estatísticas do GitHub são atualizadas diariamente.
Projetos relacionados
A cross-platform desktop app for upscaling images with super-resolution models, supporting built-in or custom models on Windows, macOS, and Linux.
7,4 mil525TypeScriptBSD-3-ClauseAtualizado anteontem
A PyTorch-based open-source framework for deep learning on healthcare imaging data, covering preprocessing, networks, losses and evaluation metrics.
8,8 mil1,7 milPythonApache-2.0Atualizado há 12 horas
A lightweight zipvoice-based text-to-speech model for voice cloning, generating 48kHz speech at up to 150x realtime on GPU.
5,5 mil0PythonApache-2.0Atualizado há 5 meses
A collection of 419 pre-trained AI models covering vision, speech, NLP, and LLMs, each runnable from a simple CLI with automatic weight download.
IA e Machine Learning#deep-learning#pretrained-models#computer-vision#speech-recognition#object-detection
2,4 mil0PythonOtherAtualizado ontem
A video LLM trained with streaming speech transcription so it can produce real-time commentary on video, with Gradio and CLI demos.
4800PythonSem licençaAtualizado há 12 meses